view notebooks/test_hubness.ipynb @ 30:e8084526f7e5 branch-tests

additional test functions

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 2,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import pickle\n",
    "from scipy.stats import pearsonr\n",
    "from scipy.stats import skew\n",
    "import sys\n",
    "from sklearn.metrics.pairwise import pairwise_distances\n",
    "%matplotlib inline\n",
    "import matplotlib.pyplot as plt\n",
    "\n",
    "%load_ext autoreload\n",
    "%autoreload 2\n",
    "\n",
    "sys.path.append('../')\n",
    "import scripts.outliers as outliers\n",
    "import scripts.utils_spatial as utils_spatial"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 3,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "name": "stdout",
     "output_type": "stream",
     "text": [
      "WARNING: there are 21 disconnected observations\n",
      "Island ids:  [3, 6, 26, 35, 39, 45, 52, 61, 62, 66, 77, 85, 94, 97, 98, 102, 103, 107, 110, 120, 121]\n",
      "Antigua and Barbuda\n",
      "Australia\n",
      "Cuba\n",
      "Fiji\n",
      "French Polynesia\n",
      "Grenada\n",
      "Iceland\n",
      "Jamaica\n",
      "Japan\n",
      "Kiribati\n",
      "Malta\n",
      "New Zealand\n",
      "Philippines\n",
      "Puerto Rico\n",
      "Republic of Serbia\n",
      "Saint Lucia\n",
      "Samoa\n",
      "Solomon Islands\n",
      "South Korea\n",
      "The Bahamas\n",
      "Trinidad and Tobago\n"
     ]
    }
   ],
   "source": [
    "X_list, Y, Yaudio = pickle.load(open('../data/lda_data_melodia_8.pickle','rb'))\n",
    "ddf = outliers.load_metadata(Yaudio, metadata_file='../data/metadata.csv')\n",
    "w, data_countries = utils_spatial.get_neighbors_for_countries_in_dataset(Y)\n",
    "w_dict = utils_spatial.from_weights_to_dict(w, data_countries)\n",
    "Xrhy, Xmel, Xmfc, Xchr = X_list\n",
    "X = np.concatenate((Xrhy, Xmel, Xmfc, Xchr), axis=1)\n",
    "\n",
    "# global outliers\n",
    "df_global, threshold, MD = outliers.get_outliers_df(X, Y, chi2thr=0.999)"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "(8200, 380)"
      ]
     },
     "execution_count": 3,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "X.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "D = pairwise_distances(X, metric='mahalanobis')"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
    "collapsed": false
   },
   "metadata": {},
   "outputs": [],
   "source": [
    "D.shape"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
    "collapsed": false
   },
   "metadata": {},
   "outputs": [],
   "source": [
    "plt.hist(D.ravel(), bins=100);"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "def n_occurrence_from_D(D, k=10, n_items=None):\n",
    "    if n_items is None:\n",
    "        n_items = len(D)\n",
    "    sort_idx = np.argsort(D, axis=1)\n",
    "    D_k = sort_idx[:, 1:(k+1)]  # nearest neighbour is the item itself\n",
    "    N_k = np.bincount(D_k.astype(int).ravel(), minlength=n_items)\n",
    "    return N_k"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "outputs": [
      "\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
      "\u001b[0;31mNameError\u001b[0m                                 Traceback (most recent call last)",
      "\u001b[0;32m<ipython-input-1-0aacb5dec8fd>\u001b[0m in \u001b[0;36m<module>\u001b[0;34m()\u001b[0m\n\u001b[0;32m----> 1\u001b[0;31m \u001b[0mN_k\u001b[0m \u001b[0;34m=\u001b[0m \u001b[0mn_occurrence_from_D\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mD\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mk\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m100\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[0m\u001b[1;32m      2\u001b[0m \u001b[0;32mprint\u001b[0m \u001b[0mskew\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mN_k\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      3\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfigure\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      4\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mhist\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0mN_k\u001b[0m\u001b[0;34m,\u001b[0m \u001b[0mbins\u001b[0m\u001b[0;34m=\u001b[0m\u001b[0;36m100\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m;\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n\u001b[1;32m      5\u001b[0m \u001b[0mplt\u001b[0m\u001b[0;34m.\u001b[0m\u001b[0mfigure\u001b[0m\u001b[0;34m(\u001b[0m\u001b[0;34m)\u001b[0m\u001b[0;34m\u001b[0m\u001b[0m\n",
      "\u001b[0;31mNameError\u001b[0m: name 'n_occurrence_from_D' is not defined"
   "metadata": {},
   "outputs": [],
   "source": [
    "N_k = n_occurrence_from_D(D, k=100)\n",
    "print skew(N_k)\n",
    "plt.figure()\n",
    "plt.hist(N_k, bins=100);\n",
    "plt.figure()\n",
    "plt.plot(np.sort(N_k))"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 11,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": [
    "#sort_idx = np.argsort(D, axis=1)\n",
    "k = 10\n",
    "D_k = sort_idx[:, 1:(k+1)]"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 12,
   "metadata": {
    "collapsed": false
   },
   "outputs": [
    {
     "data": {
      "text/plain": [
       "array([[4650, 2942, 3520, ..., 1318, 6678, 6056],\n",
       "       [1933, 6143, 6757, ..., 7269, 4321, 1563],\n",
       "       [3170, 2549, 4860, ..., 6678, 7414, 6056],\n",
       "       ..., \n",
       "       [6016, 2243, 1616, ..., 7627, 2018,  515],\n",
       "       [7027, 4860, 6346, ...,  997, 3892, 1846],\n",
       "       [5119, 1563, 4035, ..., 3486, 7617, 3854]])"
      ]
     },
     "execution_count": 12,
     "metadata": {},
     "output_type": "execute_result"
    }
   ],
   "source": [
    "D_k"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": null,
   "metadata": {
    "collapsed": true
   },
   "outputs": [],
   "source": []
  }
 ],
 "metadata": {
  "kernelspec": {
   "display_name": "Python 2",
   "language": "python",
   "name": "python2"
  },
  "language_info": {
   "codemirror_mode": {
    "name": "ipython",
    "version": 2
   },
   "file_extension": ".py",
   "mimetype": "text/x-python",
   "name": "python",
   "nbconvert_exporter": "python",
   "pygments_lexer": "ipython2",
   "version": "2.7.12"
  }
 },
 "nbformat": 4,
 "nbformat_minor": 1
}